3D Object Detection Using Frustums and Attention Modules for Images and Point Cloudsopen access
- Authors
- Li,Yiran; Xie,Han; Shin,Hyunchul
- Issue Date
- Feb-2021
- Publisher
- Springer International Publishing AG
- Keywords
- 3D vision; attention module; fusion; point cloud; vehicle detection
- Citation
- Signals and Communication Technology, v.2, no.1, pp 98 - 107
- Pages
- 10
- Indexed
- SCOPUS
- Journal Title
- Signals and Communication Technology
- Volume
- 2
- Number
- 1
- Start Page
- 98
- End Page
- 107
- URI
- https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/113276
- DOI
- 10.3390/signals2010009
- ISSN
- 1860-4862
1860-4870
- Abstract
- Three-dimensional (3D) object detection is essential in autonomous driving. Threedimensional (3D) Lidar sensor can capture three-dimensional objects, such as vehicles, cycles, pedestrians, and other objects on the road. Although Lidar can generate point clouds in 3D space, it
still lacks the fine resolution of 2D information. Therefore, Lidar and camera fusion has gradually
become a practical method for 3D object detection. Previous strategies focused on the extraction
of voxel points and the fusion of feature maps. However, the biggest challenge is in extracting
enough edge information to detect small objects. To solve this problem, we found that attention
modules are beneficial in detecting small objects. In this work, we developed Frustum ConvNet and
attention modules for the fusion of images from a camera and point clouds from a Lidar. Multilayer
Perceptron (MLP) and tanh activation functions were used in the attention modules. Furthermore,
the attention modules were designed on PointNet to perform multilayer edge detection for 3D object
detection. Compared with a previous well-known method, Frustum ConvNet, our method achieved
competitive results, with an improvement of 0.27%, 0.43%, and 0.36% in Average Precision (AP) for
3D object detection in easy, moderate, and hard cases, respectively, and an improvement of 0.21%,
0.27%, and 0.01% in AP for Bird’s Eye View (BEV) object detection in easy, moderate, and hard cases,
respectively, on the KITTI detection benchmarks. Our method also obtained the best results in four
cases in AP on the indoor SUN-RGBD dataset for 3D object detection.
Keywords: 3D vision; attention module; fusion; point cloud; vehicle detection
- Files in This Item
-
Go to Link
- Appears in
Collections - COLLEGE OF ENGINEERING SCIENCES > SCHOOL OF ELECTRICAL ENGINEERING > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/113276)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.